INDEX

Explanations

elements that quantify comparisons and distinctions among multiple items or categories

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸ĢåĪĩ

-0.20

avail

-0.17

Ð¾Ð´Ð°Ð²

-0.16

 semua

-0.15

elper

-0.14

 everything

-0.14

Î¯Îº

-0.14

æķ·

-0.14

all

-0.14

oni

-0.14

POSITIVE LOGITS

 unique

0.28

ä¸įåĲĮçļĦ

0.24

unique

0.24

 differently

0.24

 different

0.24

 respective

0.23

 separately

0.23

 distinct

0.22

.unique

0.22

çį¨

0.22

Activations Density 0.173%

elements that quantify comparisons and distinctions among multiple items or categories

No Comments

No Known Activations